Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     color
    -0.06
    ẹn
    -0.06
     tum
    -0.06
     hazardous
    -0.06
     driven
    -0.06
     Voy
    -0.06
     Wu
    -0.06
     savun
    -0.06
     EDUC
    -0.06
     Daddy
    -0.06
    POSITIVE LOGITS
    學
    0.08
    +");↵
    0.06
     '='
    0.06
    urgeon
    0.06
     lesbienne
    0.06
     بیان
    0.06
    効
    0.06
    finity
    0.06
    _DISPATCH
    0.06
    olah
    0.06
    Act Density 0.557%

    No Known Activations